/chat/completions API requests are routed the lowest cost provider and model that satisfies those requirements. All instruments have zero data retention and support:| Instrument | Quality | Latency | Throughput | Price | 30D Average |
|---|---|---|---|---|---|
| text-max | - | - | |||
| text-prime | - | - | |||
| text-standard | - | - |
curl -L https://api.thegrid.ai/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer <YOUR_API_KEY>" \ -d '{ "model": "text-max", "max_tokens": 50, "messages": [ {"role": "system", "content": "Be extremely brief. One sentence max."}, {"role": "user", "content": "Why does AI inference need a market?"} ] }'